Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for a motorized mobile system (MMS) comprising: generating first sensor data about an object from a first sensor with respect to a first sensor reference frame, wherein the first sensor data about the object comprises a first range measurement to the object and a first bearing measurement to the object, the first range measurement having an associated first uncertainty, and the first bearing measurement having an associated second uncertainty; generating second sensor data about the object from a second sensor with respect to a second sensor reference frame, wherein the second sensor data about the object comprises a second range measurement to the object and a second bearing measurement to the object, the second range measurement having an associated third uncertainty, and the second bearing measurement having an associated fourth uncertainty; receiving, by a processor, the first and second sensor data; responsive to receiving the first and second sensor data, matching, by the processor, the first and second sensor data by time; responsive to matching the first and second sensor data by time, determining, by the processor, whether one or more of the matching first and second sensor data comprises polar coordinates; responsive to determining one or more of the matching first and second sensor data comprises polar coordinates, converting, by the processor, the one or more matching first and second sensor data comprising polar coordinates to Cartesian coordinates; translating, by the processor, the first sensor data from the first sensor reference frame to a Cartesian coordinate system of a motorized mobile system reference frame; translating, by the processor, the second sensor data from the second sensor reference frame to the Cartesian coordinate system of the motorized mobile system reference frame; selecting, by the processor, a lower range uncertainty between the first uncertainty and the third uncertainty; selecting, by the processor, a lower bearing uncertainty between the second uncertainty and the fourth uncertainty; and combining, by the processor, the bearing measurement associated with the selected lower bearing uncertainty and the range measurement associated with the selected lower range uncertainty as a location of the object within a reduced area of uncertainty in the Cartesian coordinate system of the motorized mobile system reference frame.
This invention relates to improving object localization in motorized mobile systems (MMS) by integrating sensor data from multiple sensors with different uncertainties. The problem addressed is the challenge of accurately determining an object's position when using sensors that provide measurements with varying degrees of uncertainty in both range and bearing. The solution involves a method that processes sensor data from at least two sensors, each providing range and bearing measurements to an object, along with their associated uncertainties. The method first synchronizes the sensor data by time and checks if the measurements are in polar coordinates, converting them to Cartesian coordinates if necessary. The data is then translated into a common Cartesian coordinate system aligned with the MMS reference frame. The method selects the range and bearing measurements with the lowest uncertainties from the available sensor data and combines them to determine the object's location. This approach reduces the overall uncertainty in the object's position by leveraging the most reliable measurements from each sensor, resulting in a more accurate and precise localization within the MMS's coordinate system. The technique is particularly useful in applications where multiple sensors with different characteristics are used, such as autonomous vehicles or robotic systems.
2. The method of claim 1 wherein the processor uses the location of the object within the reduced area of uncertainty for at least one navigation operation.
This invention relates to object detection and navigation systems, particularly for improving the accuracy of navigation operations by reducing uncertainty in object location. The system involves detecting an object within a defined area and refining its position to a smaller area of uncertainty. The processor then uses this refined location for navigation tasks, such as obstacle avoidance, path planning, or autonomous vehicle control. The method ensures that navigation decisions are based on a more precise object position, enhancing safety and efficiency. The system may integrate sensor data, such as from cameras, lidar, or radar, to initially detect the object and then apply filtering or tracking algorithms to narrow down its location. The reduced uncertainty area is dynamically adjusted based on sensor accuracy, environmental conditions, or object movement. By leveraging this refined position, the navigation system can make more informed decisions, such as adjusting trajectories or avoiding collisions. The invention is particularly useful in autonomous vehicles, robotics, and other applications requiring precise spatial awareness.
3. The method of claim 1 wherein the processor uses the location of the object within the reduced area of uncertainty for obstacle avoidance.
This invention relates to obstacle avoidance systems for autonomous vehicles or robotic devices. The system uses sensor data to detect objects in the environment and determines a reduced area of uncertainty for the object's location. The processor then utilizes this refined location information to avoid collisions with the detected object. The method involves processing sensor data to identify objects, estimating the object's position with improved accuracy, and applying this positional data to navigate around obstacles. The reduced area of uncertainty is derived from sensor fusion techniques, such as combining data from multiple sensors like cameras, lidar, or radar, to narrow down the object's possible location. By refining the object's position, the system can make more precise decisions for path planning and obstacle avoidance, improving safety and efficiency in autonomous navigation. The invention addresses challenges in real-time obstacle detection and avoidance, particularly in dynamic or cluttered environments where sensor data may be noisy or incomplete. The processor's use of the object's location within the reduced uncertainty area enables more accurate and reliable collision avoidance maneuvers.
4. The method of claim 1 wherein the processor identifies the location of the object within the reduced area of uncertainty on a situational awareness map.
This invention relates to object detection and tracking systems, particularly for identifying and locating objects within a reduced area of uncertainty on a situational awareness map. The technology addresses the challenge of accurately determining the position of objects in dynamic environments where initial detection may have a broad area of uncertainty. The system first detects an object and estimates an initial area of uncertainty for its location. Using sensor data and processing algorithms, the system refines this area to a smaller, more precise region. A processor then analyzes the refined data to pinpoint the object's exact location within this reduced uncertainty area. The situational awareness map visually represents this location, providing real-time tracking and situational context. The method improves accuracy in object localization, which is critical for applications such as autonomous navigation, surveillance, and collision avoidance. The system may integrate multiple sensors, including radar, lidar, or cameras, to enhance detection and tracking performance. The processor employs filtering techniques, such as Kalman or particle filters, to refine the object's position estimate over time. The situational awareness map dynamically updates to reflect the latest location data, ensuring users or automated systems have precise and actionable information. This approach reduces false positives and improves decision-making in time-sensitive scenarios.
5. The method of claim 1 wherein the first uncertainty is larger than the second uncertainty, and the fourth uncertainty is larger than the third uncertainty.
This invention relates to a method for improving the accuracy of measurements or predictions in systems where uncertainties are present. The method addresses the challenge of reducing errors in outputs when input data or models have inherent uncertainties. The core approach involves comparing and adjusting uncertainties associated with different stages of the process to enhance overall reliability. The method operates by evaluating two sets of uncertainties: a first uncertainty and a second uncertainty, where the first is larger than the second, and a third uncertainty and a fourth uncertainty, where the fourth is larger than the third. These uncertainties may arise from different sources, such as measurement noise, model approximations, or environmental variability. By systematically comparing these uncertainties, the method ensures that the larger uncertainties are appropriately weighted or mitigated, while the smaller uncertainties are retained or refined. The process may involve techniques such as statistical filtering, error propagation analysis, or adaptive weighting to balance the influence of each uncertainty on the final output. The method can be applied in various fields, including sensor networks, predictive modeling, and control systems, where minimizing uncertainty is critical for performance. By ensuring that larger uncertainties are managed more rigorously, the method improves the robustness and accuracy of the system's outputs.
6. The method of claim 1 wherein the processor retrieves the first, second, third, and fourth uncertainties from a memory.
A system and method for uncertainty management in computational processes involves retrieving multiple uncertainty values from a memory to improve decision-making or analysis. The method addresses the challenge of handling multiple sources of uncertainty in computational tasks, such as simulations, predictions, or data processing, where different types of uncertainties (e.g., measurement errors, model inaccuracies, or environmental variations) must be accounted for to ensure reliable results. The processor retrieves four distinct uncertainty values—first, second, third, and fourth—from a memory, where each value represents a different source or type of uncertainty. These uncertainties may include statistical errors, systematic biases, or probabilistic variations. The retrieved uncertainties are then used to adjust calculations, refine models, or generate more accurate outputs. This approach enhances the robustness of computational systems by explicitly incorporating multiple uncertainty factors, leading to more reliable and trustworthy results in applications such as scientific research, engineering simulations, or decision support systems. The method ensures that all relevant uncertainties are considered, reducing the risk of errors or misinterpretations in the final output.
7. The method of claim 1 wherein uncertainty comprises known error in a physical measurement.
A system and method for reducing uncertainty in physical measurements, particularly in scenarios where measurement errors are known or can be estimated. The invention addresses the challenge of improving the accuracy of measurements in fields such as scientific research, industrial processes, and engineering applications, where precise data is critical. The method involves identifying and quantifying known errors in physical measurements, such as those arising from instrument calibration, environmental factors, or inherent measurement limitations. By incorporating these known errors into a computational model, the system adjusts the measurement data to compensate for the identified uncertainties. This adjustment process may involve statistical techniques, error propagation analysis, or machine learning algorithms to refine the measurement values. The system can also integrate multiple measurement sources to cross-validate data and further reduce uncertainty. The method is particularly useful in applications where high precision is required, such as in aerospace, medical diagnostics, or environmental monitoring. The invention ensures that measurement data is more reliable and accurate, leading to better decision-making and improved outcomes in various technical and scientific domains.
8. The method of claim 1 wherein the motorized mobile system is selected as a mobile chair, a mobility scooter, an electronic conveyance vehicle, a riding lawn mower, a grocery cart, an all-terrain vehicle, an off-road vehicle, or a golf cart.
This invention relates to motorized mobile systems designed to assist users in navigating various environments. The technology addresses the need for versatile, user-friendly mobility solutions that can adapt to different terrains and applications. The system includes a motorized mobile platform, such as a chair, scooter, electronic conveyance vehicle, riding lawn mower, grocery cart, all-terrain vehicle, off-road vehicle, or golf cart, equipped with features to enhance mobility and usability. The platform may incorporate sensors, control mechanisms, and user interfaces to optimize movement, stability, and ease of operation. For example, the system may adjust speed, direction, or balance based on environmental conditions or user input. The invention aims to provide a flexible mobility solution that can be tailored to specific use cases, whether for personal transportation, recreational activities, or commercial applications. The design ensures compatibility with different user needs, including those requiring assistance with mobility due to physical limitations or those seeking efficient transportation in challenging environments. The system may also include safety features, such as obstacle detection or emergency braking, to ensure secure operation. Overall, the invention enhances accessibility and convenience for users across various motorized mobile applications.
9. The method of claim 1 wherein the object comprises at least one of a physical thing, a person, an animal, a ground feature, and a surface condition.
This invention relates to object detection and tracking systems, particularly for identifying and monitoring various types of objects in a given environment. The technology addresses the challenge of accurately detecting and classifying diverse objects, including physical things, people, animals, ground features, and surface conditions, in real-time applications such as surveillance, autonomous navigation, or environmental monitoring. The method involves capturing data from one or more sensors, such as cameras, lidar, or radar, to detect objects within a field of view. The system processes this data to identify and classify objects based on their characteristics, such as shape, movement, or texture. The classification step distinguishes between different object types, including physical objects, living beings (people or animals), natural or man-made ground features (e.g., terrain, roads), and surface conditions (e.g., ice, water, or debris). Once identified, the system tracks the objects over time, updating their positions and states as they move or change. The tracking may involve predictive algorithms to anticipate object behavior or environmental changes. The method ensures robust detection and classification by adapting to varying conditions, such as lighting, weather, or sensor noise. This approach improves accuracy in applications requiring precise object recognition, such as autonomous vehicles, security systems, or industrial automation, by handling a wide range of object types in dynamic environments.
10. The method of claim 1 wherein the first sensor is selected as at least one of an optical sensor, a sound sensor, a hall effect sensor, a proximity sensor, a radar sensor, a sonar sensor, an ultrasonic sensor, a LIDAR sensor, and a camera capable of distance detection.
This invention relates to a method for selecting and utilizing sensors in a system to detect and measure environmental or object parameters. The method addresses the challenge of accurately and reliably gathering data from various sensors in dynamic environments where different sensor types may be required for optimal performance. The system employs at least one sensor, which can be an optical sensor, sound sensor, Hall effect sensor, proximity sensor, radar sensor, sonar sensor, ultrasonic sensor, LIDAR sensor, or a camera with distance detection capabilities. These sensors are chosen based on their ability to detect specific parameters such as distance, presence, or movement of objects. The method ensures that the selected sensor provides accurate and timely data, improving the overall functionality of the system. The system may also include additional sensors or processing units to enhance data accuracy and reliability. The invention is particularly useful in applications requiring precise environmental monitoring, object tracking, or navigation in autonomous systems.
11. The method of claim 1 wherein the second sensor is selected as at least one of an optical sensor, a sound sensor, a hall effect sensor, a proximity sensor, a radar sensor, a sonar sensor, an ultrasonic sensor, a LIDAR sensor, and a camera capable of distance detection.
This invention relates to sensor-based systems for detecting and monitoring objects or conditions in an environment. The technology addresses the need for accurate and versatile sensing in applications such as automation, robotics, and environmental monitoring, where traditional sensors may lack precision or adaptability. The method involves using a primary sensor to detect an object or condition and a secondary sensor to verify or supplement the primary detection. The secondary sensor is selected from a range of sensor types, including optical sensors, sound sensors, Hall effect sensors, proximity sensors, radar sensors, sonar sensors, ultrasonic sensors, LIDAR sensors, and cameras with distance detection capabilities. These sensors provide different detection mechanisms, allowing the system to adapt to various environmental conditions and object characteristics. For example, optical sensors may detect light reflections, while radar or LIDAR sensors can measure distance and movement. The selection of the secondary sensor depends on the specific requirements of the application, such as accuracy, range, or environmental factors like lighting or interference. By incorporating multiple sensor types, the system improves detection reliability, reduces false positives, and enhances overall performance in dynamic environments. This approach is particularly useful in applications where a single sensor type may be insufficient, such as in autonomous navigation, industrial automation, or safety monitoring. The method ensures robust and flexible sensing capabilities across diverse scenarios.
12. The method of claim 1 wherein the first sensor determines the first range measurement as a distance to the object from a point of operation of the first sensor.
A system and method for object detection and ranging involves using multiple sensors to determine the position and distance of an object relative to a reference point. The primary sensor measures the distance from a specific operational point to the object, providing a direct range measurement. This measurement is used to establish a baseline for further calculations or adjustments. Additional sensors may be employed to refine the measurement or provide complementary data, such as angular position or relative movement. The system is designed to enhance accuracy in dynamic environments where objects may be moving or where environmental factors could affect sensor performance. The method ensures precise distance determination by leveraging the operational point of the primary sensor as a fixed reference, reducing errors caused by sensor misalignment or environmental interference. This approach is particularly useful in applications requiring high-precision ranging, such as autonomous navigation, industrial automation, or collision avoidance systems. The system may incorporate calibration techniques to maintain accuracy over time and under varying conditions. By integrating multiple sensor inputs, the method improves reliability and robustness in object detection and ranging tasks.
13. The method of claim 1 wherein the first sensor determines the first bearing measurement as a direction to the object from a point of operation of the first sensor.
This invention relates to a system for determining the bearing of an object using multiple sensors. The problem addressed is accurately identifying the direction to an object from a sensor's operational position, which is critical in applications like navigation, surveillance, or autonomous systems where precise directional data is required. The method involves using at least two sensors to measure the bearing of an object. The first sensor determines a first bearing measurement as the direction to the object from the sensor's point of operation. The second sensor, positioned at a different location, measures a second bearing to the same object. By combining these measurements, the system calculates the object's position relative to the sensors. The method may also include adjusting the measurements to account for environmental factors or sensor inaccuracies, ensuring higher precision. The system can be used in various environments, including those with obstacles or interference, by dynamically selecting the best sensors for measurement. The invention improves upon prior systems by providing a more reliable and accurate way to determine an object's bearing, reducing errors caused by single-sensor limitations.
14. The method of claim 13 wherein the direction to the object is expressed in degrees offset from a true baseline direction.
A system and method for determining the direction to an object using a compass or similar directional sensor. The technology addresses the challenge of accurately identifying the orientation of an object relative to a known reference point, which is critical in navigation, surveying, and autonomous systems. The method involves measuring the direction to the object using a compass or other directional sensor, where the direction is expressed in degrees offset from a true baseline direction, such as true north. This allows for precise angular measurements relative to a standardized reference, improving accuracy in applications requiring directional data. The system may include a compass module that provides the directional measurement, a processing unit that calculates the offset from the baseline, and an output interface to display or transmit the directional information. The method ensures consistency and reliability in directional measurements, which is essential for applications such as robotics, geolocation, and environmental monitoring. The system may also incorporate error correction mechanisms to account for magnetic interference or sensor drift, further enhancing the accuracy of the directional data.
15. The method of claim 1 wherein the second sensor determines the second range measurement as a distance to the object from a point of operation of the second sensor.
A system and method for object detection and ranging involves multiple sensors working together to determine the position and distance of an object. The primary sensor generates a first range measurement to the object, while a secondary sensor provides a second range measurement as a distance from the object to the secondary sensor's point of operation. The system combines these measurements to improve accuracy, reliability, or coverage in detecting and locating objects. This approach is particularly useful in applications where a single sensor may have limitations, such as blind spots, interference, or reduced precision. By using multiple sensors with different perspectives or measurement techniques, the system can compensate for these limitations and provide more robust object detection. The secondary sensor's measurement is taken from its operational point, ensuring that the distance is measured relative to its specific location, which may differ from the primary sensor's position. This method enhances the overall performance of the detection system by leveraging complementary data from multiple sources.
16. The method of claim 1 wherein the second sensor determines the second bearing measurement as a direction to the object from a point of operation of the first sensor.
A system and method for determining the position of an object using multiple sensors. The invention addresses the challenge of accurately locating an object in an environment where a single sensor may not provide sufficient precision or reliability. The method involves using a first sensor to detect the object and generate a first bearing measurement, which represents the direction from the first sensor to the object. A second sensor, positioned at a different location, then determines a second bearing measurement, which is the direction from the second sensor to the object. By combining these two bearing measurements, the system calculates the precise position of the object. The second sensor's measurement is taken from its own point of operation, ensuring that the directional data is independent of the first sensor's perspective. This dual-sensor approach improves accuracy by reducing errors caused by environmental factors or sensor limitations. The method is particularly useful in applications requiring high-precision object tracking, such as navigation, surveillance, or autonomous systems. The system may include additional sensors or processing steps to further refine the object's position.
17. The method of claim 16 wherein the direction to the object is expressed in degrees offset from a true baseline direction.
A system and method for determining the direction to an object relative to a baseline direction. The method involves capturing an image of the object using a camera, processing the image to identify the object, and calculating the direction to the object based on the object's position in the image. The direction is expressed in degrees offset from a true baseline direction, such as magnetic north or a fixed reference axis. The system may include a camera, a processor, and a compass or other directional sensor to establish the baseline direction. The method may further include compensating for environmental factors, such as magnetic interference or camera misalignment, to improve accuracy. The system may be used in navigation, tracking, or surveillance applications where precise directional information is required. The method ensures that the direction to the object is consistently measured and reported relative to a standardized baseline, enhancing reliability in applications where directional accuracy is critical.
18. The method of claim 1 wherein the processor processes the first uncertainty as a parameter, associated with a result of the first range measurement, that characterizes a dispersion of values that could reasonably be attributed to the first range measurement.
This invention relates to range measurement systems, particularly those that account for uncertainty in measurements. The technology addresses the challenge of accurately characterizing the variability or dispersion in range measurements, which is critical for applications requiring precise distance determination, such as autonomous navigation, robotics, and sensor networks. The method involves processing a first range measurement to determine its associated uncertainty, treating this uncertainty as a parameter that quantifies the possible dispersion of values reasonably attributable to the measurement. This parameter helps assess the reliability and precision of the range measurement, allowing systems to make more informed decisions based on the data. The uncertainty parameter can be derived from statistical analysis, sensor noise models, or environmental factors affecting the measurement. Additionally, the method may involve comparing the first range measurement and its uncertainty with a second range measurement and its corresponding uncertainty to determine consistency or discrepancies between the two. This comparison can help identify measurement errors, improve accuracy, or refine calibration in systems relying on multiple range measurements. The approach ensures that uncertainty is explicitly considered in decision-making processes, enhancing the robustness of range-based applications.
19. The method of claim 1 , wherein the processor processes the second uncertainty as a parameter, associated with a result of the first bearing measurement, that characterizes a dispersion of values that could reasonably be attributed to the first bearing measurement.
This invention relates to systems for processing bearing measurements, particularly in applications where measurement uncertainty must be quantified and propagated. The problem addressed is the need to accurately represent and handle uncertainty in bearing measurements, which is critical in navigation, robotics, and sensor fusion applications where precise directional data is required. The method involves processing a second uncertainty parameter that characterizes the dispersion of possible values attributable to a first bearing measurement. This second uncertainty is treated as a parameter associated with the result of the first bearing measurement, allowing for a probabilistic or statistical representation of the measurement's reliability. By incorporating this uncertainty, the system can better account for variations in the measurement process, such as sensor noise, environmental interference, or systematic errors. The method may also involve generating the first bearing measurement using a sensor, such as an inertial measurement unit (IMU) or a compass, and determining the second uncertainty based on factors like sensor calibration data, environmental conditions, or historical measurement patterns. The processed uncertainty can then be used in subsequent calculations, such as sensor fusion algorithms or navigation systems, to improve the accuracy and robustness of the overall system. This approach ensures that bearing measurements are not treated as absolute values but are instead associated with a confidence interval, enabling more reliable decision-making in applications where directional accuracy is critical.
20. The method of claim 19 wherein the target is selected as at least one of an optical target, a retro-reflective target, a graphic, a sticker, and a decal.
The invention relates to a method for selecting and processing targets in a visual tracking or recognition system. The method addresses the challenge of accurately identifying and tracking various types of targets in different environments, ensuring reliable performance across diverse applications. The system is designed to work with multiple target types, including optical targets, retro-reflective targets, graphics, stickers, and decals. These targets may be used in applications such as augmented reality, robotics, industrial automation, or navigation systems, where precise tracking is essential. The method involves detecting and distinguishing these targets based on their visual or reflective properties, allowing the system to adapt to different target materials and configurations. By supporting a wide range of target types, the invention enhances flexibility and accuracy in tracking applications, reducing errors caused by environmental factors or target variations. The system may also include preprocessing steps to improve target detection, such as filtering or enhancing the input data to optimize recognition performance. This method ensures robust tracking in dynamic or complex environments, making it suitable for high-precision applications.
21. The method of claim 1 wherein the processor processes the third uncertainty as a parameter, associated with a result of the second range measurement, that characterizes a dispersion of values that could reasonably be attributed to the second range measurement.
This invention relates to range measurement systems, particularly those that account for uncertainties in measurements. The technology addresses the challenge of accurately determining distances in environments where measurement errors or variations can occur, such as in radar, lidar, or other sensing applications. The invention improves upon prior systems by incorporating uncertainty parameters to better characterize the reliability of range measurements. The method involves processing a third uncertainty parameter associated with a second range measurement. This parameter quantifies the dispersion or variability of possible values that could reasonably be attributed to the second range measurement, effectively capturing the range of plausible outcomes due to noise, environmental factors, or system limitations. By treating this uncertainty as a measurable parameter, the system can refine its calculations, improve accuracy, and provide more reliable distance estimates. The method may also involve comparing the second range measurement with a first range measurement and adjusting the uncertainty parameter based on this comparison to further enhance precision. This approach ensures that the system dynamically adapts to measurement conditions, reducing errors in distance determinations. The invention is particularly useful in applications requiring high-precision ranging, such as autonomous navigation, robotics, and environmental monitoring.
22. The method of claim 1 , wherein the processor processes the fourth uncertainty as a parameter, associated with a result of the second bearing measurement, that characterizes a dispersion of values that could reasonably be attributed to the second bearing measurement.
This invention relates to systems for processing bearing measurements, particularly in navigation or positioning applications where measurement uncertainty must be accounted for. The method involves analyzing bearing measurements to determine their reliability and accuracy, with a focus on quantifying and processing uncertainty in these measurements. The method processes a fourth uncertainty parameter, which is associated with a result of a second bearing measurement. This parameter characterizes the dispersion of values that could reasonably be attributed to the second bearing measurement, effectively representing the range of possible deviations from the measured value. By incorporating this uncertainty parameter, the system can better assess the confidence level of the bearing measurement and improve the accuracy of navigation or positioning calculations. The method also involves processing a first bearing measurement and a second bearing measurement, where the second bearing measurement is derived from the first bearing measurement or another source. The system may apply statistical or probabilistic techniques to evaluate the uncertainty in these measurements, ensuring that the final position or orientation estimates account for potential errors. This approach is particularly useful in applications where precise positioning is critical, such as autonomous navigation, robotics, or surveying. By explicitly modeling measurement uncertainty, the system can provide more reliable and robust results.
23. The method of claim 22 wherein the target is selected as at least one of an optical target, a retro-reflective target, a graphic, a pattern, a sticker, and a decal.
This invention relates to a method for selecting and processing targets in a visual tracking or recognition system. The method addresses the challenge of accurately identifying and tracking various types of targets in different environments, ensuring reliable performance across diverse applications. The system selects a target from a predefined set of options, including optical targets, retro-reflective targets, graphics, patterns, stickers, and decals. These targets may be used in applications such as augmented reality, robotics, industrial automation, or navigation systems, where precise tracking of visual markers is essential. The method ensures compatibility with different target types, allowing flexibility in deployment. The system may also include preprocessing steps to enhance target detection, such as image filtering or contrast adjustment, to improve accuracy in varying lighting conditions. Additionally, the method may incorporate machine learning techniques to adapt to different target characteristics dynamically. The invention aims to provide a robust solution for target selection and tracking, ensuring consistent performance across various target types and environmental conditions.
24. The method of claim 1 wherein at least one of the first and second sensors is located on a vehicle other than the motorized mobile system, and the processor receives data about the object from the at least one of the first and second sensors located on the vehicle other than the motorized mobile system.
This invention relates to a system for detecting and tracking objects in an environment using multiple sensors, particularly for applications involving motorized mobile systems such as autonomous vehicles. The primary challenge addressed is improving object detection accuracy and reliability by leveraging data from multiple sensors, including those not directly mounted on the motorized mobile system. The system includes at least two sensors, which may be of different types (e.g., cameras, lidar, radar) and may be located on the motorized mobile system or on other nearby vehicles. A processor receives sensor data from these sources and processes it to detect and track objects in the environment. By incorporating data from sensors on external vehicles, the system enhances situational awareness, reduces blind spots, and improves detection accuracy, especially in complex or dynamic environments. The processor may use the combined sensor data to determine the position, velocity, and trajectory of objects, enabling the motorized mobile system to navigate safely and efficiently. The system may also include communication modules to transmit and receive sensor data between the motorized mobile system and other vehicles, ensuring real-time data sharing. This approach improves object detection performance by leveraging additional sensor inputs beyond those available on a single vehicle, enhancing safety and operational capabilities in autonomous or semi-autonomous systems.
25. The method of claim 1 wherein a target is associated with the object, and the first sensor measures a range and a bearing to the target associated with the object, generates the range to the target as the first range measurement to the object, and generates the bearing to the target as the first bearing measurement to the object.
This invention relates to object tracking systems that use sensor measurements to determine the position of an object. The problem addressed is accurately measuring the range and bearing of an object using a sensor, particularly when the object has an associated target that can be detected by the sensor. Traditional systems may struggle with precision or reliability in such measurements, especially in dynamic environments. The invention describes a method where a target is associated with an object, and a first sensor measures both the range and bearing to this target. The sensor generates the measured range as the first range measurement to the object and the measured bearing as the first bearing measurement to the object. This allows the system to track the object's position based on the target's detected location. The method may also involve additional sensors or processing steps to refine the measurements, ensuring accurate tracking even in challenging conditions. The use of a target associated with the object improves measurement reliability by providing a clear reference point for the sensor. This approach is useful in applications such as surveillance, navigation, or autonomous systems where precise object localization is critical.
26. The method of claim 1 wherein a target is associated with the object, and the second sensor measures a range and a bearing to the target associated with the object, generates the range to the target as the second range measurement to the object, and generates the bearing to the target as the second bearing measurement to the object.
This invention relates to object tracking systems that use multiple sensors to determine the position of an object. The problem addressed is improving the accuracy and reliability of object tracking by combining measurements from different sensors, particularly when one sensor provides range and bearing data to a target associated with the object. The method involves using a first sensor to measure a first range and a first bearing to an object. A second sensor measures a second range and a second bearing to a target that is associated with the object. The second sensor generates the range to the target as the second range measurement to the object and the bearing to the target as the second bearing measurement to the object. The system then combines these measurements to determine the object's position more accurately than either sensor could alone. This approach is useful in applications where direct measurement of the object is difficult, but an associated target can be reliably tracked. The method ensures that the second sensor's measurements are effectively treated as measurements of the object itself, improving tracking performance in scenarios with partial or indirect visibility.
28. The method of claim 1 further comprising providing one or more of orientation, attitude, and heading to the processor by an inertial measurement unit, wherein the processor uses the one or more of orientation, attitude, and heading to convert the one or more matching first and second sensor data comprising polar coordinates to the Cartesian coordinates.
This invention relates to a system for processing sensor data, particularly for converting polar coordinates to Cartesian coordinates in applications such as navigation or positioning. The system addresses the challenge of accurately transforming sensor data between coordinate systems, which is critical for applications requiring precise spatial awareness, such as autonomous vehicles, robotics, or augmented reality. The system includes a processor that receives sensor data from at least two sensors, where the data may include polar coordinates (e.g., range and angle measurements). The processor identifies matching data points from the sensors and converts these into Cartesian coordinates (e.g., x, y, z) for further processing. To enhance accuracy, the system incorporates an inertial measurement unit (IMU) that provides orientation, attitude, and heading information. The processor uses this IMU data to refine the coordinate conversion, ensuring that the transformed Cartesian coordinates are aligned with the system's reference frame. The IMU data compensates for any movement or rotation of the sensors, improving the reliability of the converted coordinates. This method is particularly useful in dynamic environments where sensor positions or orientations may change over time. The system may also include additional processing steps, such as filtering or calibration, to further enhance the accuracy of the sensor data. The overall approach ensures that the converted Cartesian coordinates are precise and usable for navigation, mapping, or other spatial applications.
29. A method for a motorized mobile system (MMS) comprising: generating first sensor data about an object from a first sensor with respect to a first sensor reference frame, the object located proximate to the motorized mobile system, wherein the first sensor data about the object comprises a first range measurement to the object and a first bearing measurement to the object, the first range measurement having an associated first uncertainty, and the first bearing measurement having an associated second uncertainty; generating second sensor data about the object from a second sensor with respect to a second sensor reference frame, the object located proximate to the motorized mobile system, wherein the second sensor data about the object comprises a second range measurement to the object and a second bearing measurement to the object, the second range measurement having an associated third uncertainty, and the second bearing measurement having an associated fourth uncertainty; receiving, by a processor, the first and second sensor data; responsive to receiving the first and second sensor data, matching, by the processor, the first and second sensor data by time; responsive to matching the first and second sensor data by time, determining, by the processor, whether one or more of the matching first and second sensor data comprises polar coordinates; responsive to determining one or more of the matching first and second sensor data comprises polar coordinates, converting, by the processor, the one or more matching first and second sensor data comprising polar coordinates to Cartesian coordinates; translating, by the processor, the first sensor data from the first sensor reference frame to a Cartesian coordinate system of a motorized mobile system reference frame; translating, by the processor, the second sensor data from the second sensor reference frame to the Cartesian coordinate system of the motorized mobile system reference frame; selecting, by the processor, a lower range uncertainty between the first uncertainty and the third uncertainty; selecting, by the processor, a lower bearing uncertainty between the second uncertainty and the fourth uncertainty; and combining, by the processor, the bearing measurement associated with the selected lower bearing uncertainty and the range measurement associated with the selected lower range uncertainty as a location of the object within a reduced area of uncertainty in the Cartesian coordinate system of the motorized mobile system reference frame.
The invention relates to a method for improving object localization in motorized mobile systems (MMS) by integrating sensor data from multiple sensors to reduce positional uncertainty. The problem addressed is the inherent inaccuracies in range and bearing measurements from individual sensors, which lead to larger uncertainty areas when determining an object's location. The method involves using at least two sensors, each providing range and bearing measurements to an object in their respective reference frames. Each measurement has associated uncertainties. The sensor data is time-matched, and if any data is in polar coordinates, it is converted to Cartesian coordinates. Both sets of sensor data are then translated into a common Cartesian coordinate system aligned with the MMS reference frame. The method selects the range and bearing measurements with the lowest uncertainties from the two sensors and combines them to determine the object's location, resulting in a reduced uncertainty area. This approach leverages the strengths of multiple sensors to achieve more precise object localization, which is critical for applications such as autonomous navigation, obstacle avoidance, and environmental mapping in mobile systems.
Unknown
March 24, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.